Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/laurentiugabriel/learnscape/isometric-explainernpx skills add LaurentiuGabriel/learnscape --skill isometric-explainergit clone --depth 1 https://github.com/LaurentiuGabriel/learnscapeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/laurentiugabriel/learnscape/isometric-explainer)<a href="https://agentmods.dev/skills/laurentiugabriel/learnscape/isometric-explainer"><img src="https://agentmods.dev/badge/skills/laurentiugabriel/learnscape/isometric-explainer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00259 | $0.01905 |
| Opus 5 | $0.00130 | $0.00953 |
| Sonnet 5 | $0.00052 | $0.00381 |
| Haiku 4.5 | $0.00026 | $0.00191 |
Grade A, and why
isometric-explainer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Isometric explainers
You are building a place that runs a mechanism. A vehicle carries real state along roads; each stop is one step of the real thing; the vehicle stops long enough for the reader to read about the step it just performed.
This works because it turns an invisible process into a journey with geography. The reader gets sequence for free (the road), scale for free (the distance), proportion for free (the size of a building), and repetition for free (a loop in the road is a loop in the algorithm). Nothing here is decoration hung on a lecture — the animation is the explanation.
Read this file, then read references/build-order.md and follow it. The other
references are lookups for when you reach the part they cover.
The five rules
Everything else in this skill follows from these. Break one and you get a screen saver with captions.
- Compute the real thing.
model.jsmust actually do the work — the real arithmetic, the real algorithm, at reduced scale. Never interpolate between pre-baked results. When the reader drags a slider the numbers must move because the model moved. - The vehicle carries state, not cargo. The bars on its flank are the actual vector. The crates in its bed are the actual byte count. The gauge is the actual budget spent. If you could delete the vehicle's decoration without losing information, it was decoration.
- Publish a fidelity ledger. Say exactly what is computed, what is scaled
down, what is assumed, and what is faked — in the About modal and the
README. Half the educational value is the reader knowing which numbers to
trust. See
references/fidelity.md. - Pace it for reading, not watching. The first visit to a station stops for
as long as its write-up takes to read. Later visits get a beat. The reader
never has to pause to keep up. See
references/pacing.md. - One canvas, no dependencies. Canvas 2D, plain ES5-style JS in IIFEs,
<script>tags in order, no build step, no network calls. It opens fromfile://, it works offline, it deploys to any static host, and it is still readable in five years.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/template/css/styles.css 13 KB
- assets/template/index.html 9.9 KB
- assets/template/js/iso.js 17 KB runs code
- assets/template/js/main.js 11 KB runs code
- assets/template/js/model.js 5.9 KB runs code
- assets/template/js/render.js 24 KB runs code
- assets/template/js/sim.js 9.5 KB runs code
- assets/template/js/ui.js 13 KB runs code
- assets/template/js/world.js 16 KB runs code
- assets/template/README.md 7.0 KB
- references/build-order.md 7.5 KB
- references/checklist.md 4.8 KB
- references/fidelity.md 4.8 KB
- references/isometric-drawing.md 7.9 KB
- references/narration.md 4.9 KB
- references/pacing.md 5.1 KB
- scripts/smoke.mjs 4.4 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 157 lines · 259 tokens per session scan A 095ddbf3f656
isometric-explainer is a skill published in the GitHub repository LaurentiuGabriel/learnscape (111 stars, last pushed 24d ago), licensed MIT. It adds 259 tokens to every session and 1,905 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
grid-ctf-ops
Operational knowledge for the gridctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging gridctf strategies.